Closed gpastal24 closed 5 months ago
Sure. A naive extension would treat multi-person as multiple single persons and solve them using GFPose repeatedly. But better designs should model interactions between multiple people and train GFPose on a multi-person dataset.
Hello thanks for your reply, I was mostly thinking about whether it would be possible to train a variant that outputs lets say N 3D poses directly from N 2D poses or better yet directly from a heatmap representation.
I suppose it is doable.
Yeah. I agree with you. It is doable and might be worth a try.
Could this method be extended for multi person 3D HPE ?